Tools

Practical utilities for building, testing, and operating AI products.

Verify sources

Start from the official repository, docs, and license before adopting a resource.

Test a narrow workflow

Use one observable workflow to compare setup time, reliability, and maintenance burden.

Prefer open paths

Choose resources that can be inspected, self-hosted, or replaced if your constraints change.

All tools

Published resources in this category.

Open-source tool for testing prompts, agents, RAG systems, and AI security behavior.

Open-source evaluation framework for LLM applications and RAG workflows.

AI gateway and Python SDK for calling many LLM providers through OpenAI-compatible or native formats.

LLM engineering platform for observability, evals, prompt management, datasets, and traces.

Visual testing tool for Model Context Protocol servers.